Cho, Moses ADebba, PraveshMathieu, Renaud SAVan Aardt, JAsner, GNaidoo, LavenMain, Russell S2010-04-132010-04-132009-07Cho, M.A., Debba, P., and Mathieu, R.S.A. 2009. Spectral variability within species and its effects on savanna tree species discrimination. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, 12-17 July 2009, pp 191-193978-1-4244-3395-7http://hdl.handle.net/10204/4017Copyright: 2009 IEEE, International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, 12-17 July 2009Differences in within-species phenology and structure driven by factors including topography, edaphic properties, and climatic variables present important challenges for species differentiation with remote sensing in the Kruger National Park, South Africa. The objective of this study was to examine probable factors including intraspecies spectral variability and the spectral sample size that could affect remote sensing of Savanna tree species across a and-use gradient in the Kruger National park. Eighteen species were examined: Acacia gerradii, Acacia nigrescens, Combretum apiculatum, Combretum collinum, Combretum hereroense, Combretum imberbe, Combretum zeyheri, Dichrostachys cinerea, Euclea sp (E. divinurum and E. natalensis, Gymnosporia sp (G. buxifolia and G. senegalensis), Lonchocarpus capassa, Peltoforum africanum, Piliostigma thonningii, Pterocarpus rotundifolia, Sclerocarya birrea, Strychnos sp (S. madagascariensis, S. usambarensis), Terminalia sericea and Ziziphus mucronata. Discriminating species using the K-nearest neighbour (K = 1) classifier with spectral angle mapper (SAM) yielded a higher classification accuracy (48% overall accuracy) compared to 16% for the classification involving the mean spectra for each species as the training spectral set. Within-species spectral variability and the training sample size were identified as important factors affecting classification accuracy of the tree species. The authors recommend a nonparametric classifier such as K-nearest neighbour classifier for classifying and mapping tree species in a highly complex environment such as the savanna system of the Kruger National Park.enSavanna tree speciesSpectral variabilityGeoscienceSpectral angle mapperKruger National ParkPhenologyIntraspecies spectral variabilityRemote sensingConference PresentationCho, M. A., Debba, P., Mathieu, R. S., Van Aardt, J., Asner, G., Naidoo, L., & Main, R. S. (2009). Spectral variability within species and its effects on savanna tree species discrimination. IEEE. http://hdl.handle.net/10204/4017Cho, Moses A, Pravesh Debba, Renaud SA Mathieu, J Van Aardt, G Asner, Laven Naidoo, and Russel S Main. "Spectral variability within species and its effects on savanna tree species discrimination." (2009): http://hdl.handle.net/10204/4017Cho MA, Debba P, Mathieu RS, Van Aardt J, Asner G, Naidoo L, et al, Spectral variability within species and its effects on savanna tree species discrimination; IEEE; 2009. http://hdl.handle.net/10204/4017 .TY - Conference Presentation AU - Cho, Moses A AU - Debba, Pravesh AU - Mathieu, Renaud SA AU - Van Aardt, J AU - Asner, G AU - Naidoo, Laven AU - Main, Russel S AB - Differences in within-species phenology and structure driven by factors including topography, edaphic properties, and climatic variables present important challenges for species differentiation with remote sensing in the Kruger National Park, South Africa. The objective of this study was to examine probable factors including intraspecies spectral variability and the spectral sample size that could affect remote sensing of Savanna tree species across a and-use gradient in the Kruger National park. Eighteen species were examined: Acacia gerradii, Acacia nigrescens, Combretum apiculatum, Combretum collinum, Combretum hereroense, Combretum imberbe, Combretum zeyheri, Dichrostachys cinerea, Euclea sp (E. divinurum and E. natalensis, Gymnosporia sp (G. buxifolia and G. senegalensis), Lonchocarpus capassa, Peltoforum africanum, Piliostigma thonningii, Pterocarpus rotundifolia, Sclerocarya birrea, Strychnos sp (S. madagascariensis, S. usambarensis), Terminalia sericea and Ziziphus mucronata. Discriminating species using the K-nearest neighbour (K = 1) classifier with spectral angle mapper (SAM) yielded a higher classification accuracy (48% overall accuracy) compared to 16% for the classification involving the mean spectra for each species as the training spectral set. Within-species spectral variability and the training sample size were identified as important factors affecting classification accuracy of the tree species. The authors recommend a nonparametric classifier such as K-nearest neighbour classifier for classifying and mapping tree species in a highly complex environment such as the savanna system of the Kruger National Park. DA - 2009-07 DB - ResearchSpace DP - CSIR KW - Savanna tree species KW - Spectral variability KW - Geoscience KW - Spectral angle mapper KW - Kruger National Park KW - Phenology KW - Intraspecies spectral variability KW - Remote sensing LK - https://researchspace.csir.co.za PY - 2009 SM - 978-1-4244-3395-7 T1 - Spectral variability within species and its effects on savanna tree species discrimination TI - Spectral variability within species and its effects on savanna tree species discrimination UR - http://hdl.handle.net/10204/4017 ER -